| { | |
| "best_metric": 0.03938543424010277, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.91324200913242, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0182648401826484, | |
| "grad_norm": 0.8473725318908691, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.7975, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0182648401826484, | |
| "eval_loss": 1.8122729063034058, | |
| "eval_runtime": 3.8568, | |
| "eval_samples_per_second": 12.964, | |
| "eval_steps_per_second": 1.815, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0365296803652968, | |
| "grad_norm": 0.9350575804710388, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.764, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 0.995567798614502, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.0446, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0730593607305936, | |
| "grad_norm": 1.407714605331421, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.0893, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.091324200913242, | |
| "grad_norm": 1.8826767206192017, | |
| "learning_rate": 0.00015, | |
| "loss": 2.7079, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 1.0161590576171875, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.9996, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1278538812785388, | |
| "grad_norm": 1.010097861289978, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.9585, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1461187214611872, | |
| "grad_norm": 1.0560206174850464, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.7454, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1643835616438356, | |
| "grad_norm": 1.162116527557373, | |
| "learning_rate": 0.00027, | |
| "loss": 1.6178, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.182648401826484, | |
| "grad_norm": 1.4233083724975586, | |
| "learning_rate": 0.0003, | |
| "loss": 1.5871, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2009132420091324, | |
| "grad_norm": 1.7879890203475952, | |
| "learning_rate": 0.0002999259840548597, | |
| "loss": 1.364, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 1.9744043350219727, | |
| "learning_rate": 0.0002997040092642407, | |
| "loss": 1.3302, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2374429223744292, | |
| "grad_norm": 2.14997935295105, | |
| "learning_rate": 0.000299334294690462, | |
| "loss": 1.1676, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2557077625570776, | |
| "grad_norm": 2.865056037902832, | |
| "learning_rate": 0.0002988172051971717, | |
| "loss": 1.179, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 2.2772552967071533, | |
| "learning_rate": 0.00029815325108927063, | |
| "loss": 1.0101, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2922374429223744, | |
| "grad_norm": 1.7772722244262695, | |
| "learning_rate": 0.0002973430876093033, | |
| "loss": 0.924, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3105022831050228, | |
| "grad_norm": 1.6902390718460083, | |
| "learning_rate": 0.0002963875142908121, | |
| "loss": 0.8714, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3287671232876712, | |
| "grad_norm": 1.3245774507522583, | |
| "learning_rate": 0.00029528747416929463, | |
| "loss": 0.849, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3470319634703196, | |
| "grad_norm": 1.3994680643081665, | |
| "learning_rate": 0.0002940440528515414, | |
| "loss": 0.6922, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 1.3206199407577515, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.6246, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3835616438356164, | |
| "grad_norm": 1.5602670907974243, | |
| "learning_rate": 0.0002911321153431338, | |
| "loss": 0.4424, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4018264840182648, | |
| "grad_norm": 1.6248738765716553, | |
| "learning_rate": 0.00028946647288323766, | |
| "loss": 0.3231, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4200913242009132, | |
| "grad_norm": 2.217292547225952, | |
| "learning_rate": 0.00028766319385259713, | |
| "loss": 0.4047, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 1.8803366422653198, | |
| "learning_rate": 0.00028572405786990294, | |
| "loss": 0.2903, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "grad_norm": 2.2177164554595947, | |
| "learning_rate": 0.00028365097862825513, | |
| "loss": 0.2043, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "eval_loss": 0.2833889126777649, | |
| "eval_runtime": 3.4109, | |
| "eval_samples_per_second": 14.659, | |
| "eval_steps_per_second": 2.052, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4748858447488584, | |
| "grad_norm": 2.0055646896362305, | |
| "learning_rate": 0.0002814460020065795, | |
| "loss": 0.1663, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4931506849315068, | |
| "grad_norm": 6.125588893890381, | |
| "learning_rate": 0.0002791113040505915, | |
| "loss": 0.4882, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5114155251141552, | |
| "grad_norm": 2.6787264347076416, | |
| "learning_rate": 0.00027664918882530225, | |
| "loss": 0.267, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5296803652968036, | |
| "grad_norm": 2.423906087875366, | |
| "learning_rate": 0.00027406208614118424, | |
| "loss": 0.2878, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 2.6322414875030518, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.3463, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5662100456621004, | |
| "grad_norm": 2.0104191303253174, | |
| "learning_rate": 0.00026852325185635354, | |
| "loss": 0.2524, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5844748858447488, | |
| "grad_norm": 1.3756883144378662, | |
| "learning_rate": 0.00026557698641636835, | |
| "loss": 0.1495, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6027397260273972, | |
| "grad_norm": 1.8245288133621216, | |
| "learning_rate": 0.0002625166604445689, | |
| "loss": 0.1895, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6210045662100456, | |
| "grad_norm": 1.0265326499938965, | |
| "learning_rate": 0.0002593452941132117, | |
| "loss": 0.0832, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.639269406392694, | |
| "grad_norm": 0.7454352378845215, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 0.06, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 0.8095255494117737, | |
| "learning_rate": 0.0002526820658893033, | |
| "loss": 0.064, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6757990867579908, | |
| "grad_norm": 0.7397829294204712, | |
| "learning_rate": 0.00024919677979854776, | |
| "loss": 0.0462, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6940639269406392, | |
| "grad_norm": 0.965843915939331, | |
| "learning_rate": 0.0002456135984623034, | |
| "loss": 0.048, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7123287671232876, | |
| "grad_norm": 0.4619573652744293, | |
| "learning_rate": 0.00024193605804794646, | |
| "loss": 0.02, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 1.6063387393951416, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.1591, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7488584474885844, | |
| "grad_norm": 1.861398696899414, | |
| "learning_rate": 0.00023431250667781958, | |
| "loss": 0.144, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7671232876712328, | |
| "grad_norm": 2.341588258743286, | |
| "learning_rate": 0.00023037401924684946, | |
| "loss": 0.1565, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7853881278538812, | |
| "grad_norm": 1.8141049146652222, | |
| "learning_rate": 0.00022635621236255567, | |
| "loss": 0.1546, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8036529680365296, | |
| "grad_norm": 2.6451475620269775, | |
| "learning_rate": 0.00022226305111525726, | |
| "loss": 0.1163, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 0.9599330425262451, | |
| "learning_rate": 0.00021809857496093199, | |
| "loss": 0.0565, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8401826484018264, | |
| "grad_norm": 0.49869561195373535, | |
| "learning_rate": 0.00021386689373476087, | |
| "loss": 0.0417, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8584474885844748, | |
| "grad_norm": 0.35756292939186096, | |
| "learning_rate": 0.00020957218359521706, | |
| "loss": 0.0231, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8767123287671232, | |
| "grad_norm": 0.629383385181427, | |
| "learning_rate": 0.0002052186829027017, | |
| "loss": 0.0203, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8949771689497716, | |
| "grad_norm": 0.6143040060997009, | |
| "learning_rate": 0.00020081068803679371, | |
| "loss": 0.0258, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "grad_norm": 0.9527487754821777, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.0326, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "eval_loss": 0.03938543424010277, | |
| "eval_runtime": 3.9802, | |
| "eval_samples_per_second": 12.562, | |
| "eval_steps_per_second": 1.759, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 110, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.310961668456448e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |